A job-housing information acquisition method and device
By discretizing and encoding user data entering and exiting base stations and performing Fourier transform, and by filtering base station combinations, the problem of inaccurate acquisition of work and residence information for users who do not work seven days a week and work night shifts has been solved in the existing technology, achieving higher analytical accuracy and universality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA MOBILE QUANTONG SYST INTEGRATION CO LTD
- Filing Date
- 2022-01-20
- Publication Date
- 2026-07-10
AI Technical Summary
Existing technologies cannot accurately handle users who do not work seven days a week or work night shifts when acquiring users' work and residence information, resulting in analysis results that do not match the actual situation and lacking accuracy and universality.
By acquiring user data on entering and exiting multiple base stations, performing discretization encoding and Fourier transform processing, analyzing spectral characteristics, and filtering out base station combinations that meet the work-residence characteristics, user work-residence information can be obtained.
It enables accurate acquisition of work and residence information for users who do not work a seven-day work week or work night shifts, improving the accuracy and universality of the analysis and making it adaptable to users with different work cycles.
Smart Images
Figure CN116528214B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing technology, specifically to a method, device, electronic device, and computer program product for obtaining workplace and residence information. Background Technology
[0002] In the field of acquiring users' work and residence information using signaling data, current industry and academic methods primarily involve analyzing the correlation between signaling data provided by users' mobile terminals and static geographic coordinate data, and then labeling users' stay behavior according to manually divided time segments. After pre-setting rules related to work cycles and work time periods, specific location types are associated with users' occupational information to analyze the occupations of specific groups of people.
[0003] In existing technologies, user dwell behavior is obtained by associating user signaling trajectories with static geographical locations. Then, user work and rest periods are marked by manually defining work and rest periods. Furthermore, user behavior is judged as work behavior by specifying user behavior that meets certain conditions and the place of dwelling through manually defined rules. Thus, user occupation information can be directly inferred from building attributes.
[0004] The aforementioned existing solutions only consider users with weekday work schedules and weekends off when defining work and rest periods, neglecting users who do not work a seven-day work week. Furthermore, existing technologies can only determine work and residence trajectories by manually dividing work and non-work hours, but everyone's work hours do not completely overlap. Inaccurate time trajectories can lead to errors in work-residence analysis. This means that using this method to analyze night shift users would result in analysis results that are completely opposite to the user's actual work-residence information, leading to a significant discrepancy between the analysis results and reality. Summary of the Invention
[0005] This application provides a method, device, electronic device, and computer program product for obtaining work and residence information, in order to solve the problems of low accuracy and universality of traditional methods for obtaining user work and residence information.
[0006] In a first aspect, embodiments of this application provide a method for obtaining work-residence information, including:
[0007] The system acquires user data for entering and exiting multiple base stations and discretizes and encodes it according to the user's entry and exit behavior to obtain the discrete entry and exit timing signal corresponding to each base station.
[0008] Based on the user's dwell time at each base station, each of the aforementioned discrete input / output timing signals is discretely accumulated and filled in the time domain to obtain the dwell time sequence corresponding to each base station.
[0009] Perform Fourier transform on each of the aforementioned residence time series to obtain the spectrum corresponding to each residence time series;
[0010] The user's entry and exit cycle at the corresponding base station is determined based on the amplitude peak value in each of the aforementioned spectra;
[0011] All base stations are sorted in ascending order of their entry and exit cycles, and several candidate base stations with the highest entry and exit cycles are selected.
[0012] The candidate base stations are combined in pairs to obtain multiple candidate base station combinations. Based on the ingress and egress period error of each candidate base station combination and the building labels of each candidate base station, target base station combinations that meet the work-residence characteristic conditions are selected. The user's work-residence information is obtained based on the target base station combinations.
[0013] In one embodiment, acquiring user entry and exit data across multiple base stations and discretizing and encoding it according to the user's entry and exit behavior to obtain an entry and exit time-series discrete signal corresponding to each base station includes:
[0014] The system acquires user zipper entry and exit data from multiple base stations, and discretizes the zipper entry and exit data after data cleaning according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station; wherein, the data cleaning process includes removing short-term zipper data with user dwell time less than a preset time threshold.
[0015] In one embodiment, the candidate base stations are paired to obtain multiple candidate base station combinations. Based on the ingress / egress cycle error of each candidate base station combination and the building tags of each candidate base station, a target base station combination that meets the work-residence characteristic conditions is selected. Based on the target base station combination, the user's work-residence information is obtained, including:
[0016] The candidate base stations are combined in pairs to obtain multiple candidate base station combinations, and it is determined whether each candidate base station combination meets the preset work-residence characteristic conditions.
[0017] If the ingress / egress cycle error of two candidate base stations in the candidate base station combination is less than the preset error threshold, and the building label type of at least one of the two candidate base stations is residential, then the candidate base station combination is determined to meet the work-residence characteristic conditions.
[0018] Select the target base station combination that meets the work-residence characteristics from all candidate base station combinations;
[0019] The user's work and residence information is obtained based on the target base station combination.
[0020] In one embodiment, obtaining the user's work-residence information based on the target base station combination includes:
[0021] The base station with the larger ingress / egress period in the target base station combination is identified as the user's work base station, and the other base station in the target base station combination is identified as the user's residential base station;
[0022] The user's work-residence information is obtained based on the target base station combination; wherein, the work-residence information includes one or more of the following: workplace geographic information, residence geographic information, workplace entry and exit cycle information, and residence entry and exit cycle information.
[0023] In one embodiment, after sorting all base stations in ascending order of their ingress and egress periods and selecting several candidate base stations with high rankings, and before combining the candidate base stations in pairs to obtain multiple candidate base station combinations, the method further includes:
[0024] Based on the location information of the candidate base stations, corresponding building labels are matched from a preset vector map, and the building labels are marked to correspond with the candidate base stations.
[0025] In one embodiment, the discretization encoding is an encoding method using bipolar non-return-to-zero codes.
[0026] In one embodiment, the Fourier transform processing is performed using the Fast Fourier Transform (FFT) calculation method.
[0027] Secondly, embodiments of this application provide a work-residence information acquisition device, comprising:
[0028] The data encoding module is used to acquire the user's zipper entry and exit data at multiple base stations and discretize and encode it according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station.
[0029] The sequence acquisition module is used to perform discrete accumulation and filling on each of the input and output time-series discrete signals in the time domain according to the user's dwell time at each base station, so as to obtain the dwell time sequence corresponding to each base station.
[0030] The frequency acquisition module is used to perform Fourier transform processing on each of the dwell time series to obtain the spectrum corresponding to each dwell time series;
[0031] The period determination module is used to determine the user's entry and exit period at the corresponding base station based on the amplitude peak value in each of the spectrums.
[0032] The candidate base station selection module is used to sort all base stations in ascending order of their ingress and egress cycles and select several candidate base stations that rank higher.
[0033] The work-residence information acquisition module is used to combine the candidate base stations in pairs to obtain multiple candidate base station combinations. Based on the entry and exit cycle error of each candidate base station combination and the building tags of each candidate base station, the module selects target base station combinations that meet the work-residence characteristic conditions and obtains the user's work-residence information based on the target base station combinations.
[0034] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory storing a computer program, wherein the processor executes the program to implement the steps of the job and residence information acquisition method described in the first aspect.
[0035] Fourthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the job and residence information acquisition method described in the first aspect.
[0036] The work-residence information acquisition method, device, electronic device, and computer program product provided in this application embodiment obtain the spectrum characteristics corresponding to the user's camping behavior at each base station by encoding user signaling data and performing Fourier transform. Then, the temporal and spatial characteristics of the user's behavior are obtained based on the spectrum characteristics, and the user's work-residence information is analyzed. Moreover, it is not limited by the seven-day work system or night shift work, and can accurately acquire work-residence information for ordinary users as well as users who do not work a seven-day work cycle or do not work an eight-hour daytime work system, thereby effectively improving the accuracy and universality of user work-residence information analysis. Attached Figure Description
[0037] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0038] Figure 1 This is one of the flowcharts illustrating the method for obtaining work-residence information provided in the embodiments of this application;
[0039] Figure 2 This is a second flowchart illustrating the method for obtaining work and residence information provided in the embodiments of this application;
[0040] Figure 3 This is a schematic diagram of the time-series discrete signal for entry and exit behavior provided in an embodiment of this application;
[0041] Figure 4 This is a schematic diagram of the residence time series provided in the embodiments of this application;
[0042] Figure 5This is a schematic diagram of the spectral characteristics of a discrete periodic sequence provided in an embodiment of this application;
[0043] Figure 6 This is a schematic diagram of the work-residence information acquisition device provided in the embodiments of this application;
[0044] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation
[0045] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0046] Figure 1 This is a flowchart illustrating the methods for obtaining work and residence information. (Refer to...) Figure 1 This application provides a method for obtaining work-residence information, which may include the following steps:
[0047] S1. Acquire user's zipper entry and exit data at multiple base stations and discretize and encode the data according to the user's entry and exit behavior to obtain the entry and exit time-series discrete signal corresponding to each base station. In one embodiment, the discretization encoding can adopt the bipolar non-return-to-zero code encoding method.
[0048] It should be noted that, based on the user's signaling data over a period of time, the user's entry and exit data at various base stations can be obtained. For each base station the user passes through, the user's entry and exit behavior at that base station will be recorded, i.e., the entry time and exit time. This entry and exit behavior is then discretized and encoded (e.g., 1 for entry and -1 for exit) to obtain the user's entry and exit time sequence discrete signal for each base station. It should also be noted that the longer the period of the acquired signaling data, the more accurate the final work-residence information will be. For example, analyzing two months' worth of signaling data will be more accurate and better reflect the user's true work-residence information than analyzing one month's worth of signaling data.
[0049] S2. Based on the user's dwell time at each base station, each of the aforementioned discrete input / output timing signals is discretely accumulated and filled in the time domain to obtain the dwell time sequence corresponding to each base station.
[0050] In this embodiment of the application, it is necessary to fill each of the above-mentioned discrete timing signals of entry and exit according to the user's dwell time at each base station. For example, in one-hour units, each hour of the user's dwell time at the base station is encoded as 1, and each hour of the user leaving the base station is encoded as -1, so as to obtain the user dwell state timing sampling signal (dwell time sequence) of the user at each base station.
[0051] S3. Perform Fourier transform processing on each of the dwell time series to obtain the spectrum corresponding to each dwell time series. In one embodiment, the Fourier transform processing is performed using the Fast Fourier Transform (FFT) calculation method.
[0052] The discrete Fourier transform of the above dwell time series yields its spectral characteristics. It should be noted that by performing a Fourier transform on the dwell time series, the temporal behavioral characteristics of users at the base station can be mapped onto the spectrum.
[0053] S4. Determine the user's entry and exit cycle at the corresponding base station based on the amplitude peak value in each of the spectrums.
[0054] It should be noted that the spectrum function is a function that can intuitively reflect the frequency domain characteristics of a time domain function. It can analyze different frequency components, which are reflected in different peaks of the amplitude spectrum. In the embodiments of this application, the frequency corresponding to the peak with the largest amplitude in the spectrum is used as the user's input / output frequency parameter under the base station, and the reciprocal of the frequency is the user's input / output period under the base station.
[0055] S5. Sort all base stations in ascending order of their entry and exit cycles, and select several candidate base stations that rank highly.
[0056] It should be noted that, based on the entry and exit cycles of the user at each base station obtained above, since the entry and exit cycle and the entry and exit frequency are reciprocals of each other, the smaller the entry and exit cycle, the greater the user's entry and exit frequency at that base station, and the more likely that the location of that base station is the user's workplace or residence, this application embodiment sorts all base stations in ascending order of entry and exit cycle, and selects several candidate base stations with the highest order (the number of selections can be set according to needs) for subsequent analysis.
[0057] S6. The candidate base stations are combined in pairs to obtain multiple candidate base station combinations. Based on the entry and exit cycle error of each candidate base station combination and the building labels of each candidate base station, target base station combinations that meet the work-residence characteristic conditions are selected. The user's work-residence information is obtained based on the target base station combinations.
[0058] In this embodiment, the selected candidate base stations are paired up. For example, if five candidate base stations are selected, ten candidate base station combinations can be formed. Based on the entry / exit cycle errors of the two base stations in each candidate base station combination and the building labels of the two base stations, it is determined whether they meet the preset work-residence characteristic conditions. For example, the condition can be set as follows: at least one base station in the candidate base station combination must have a building label indicating a residential area. After filtering out the target base station combinations that meet the work-residence characteristic conditions, the user's work-residence information can be further obtained based on the information of the base stations in the target base station combinations, such as the location information of the base stations and the time cycle information of the user entering and exiting the base stations (residence or workplace).
[0059] The work-residence information acquisition method provided in this application obtains the spectral characteristics corresponding to the user's camping behavior at each base station by encoding user signaling data and performing Fourier transform. Then, the temporal and spatial characteristics of user behavior are obtained based on the spectral characteristics, and the user's work-residence information is analyzed. Moreover, it is not limited by the seven-day work system or night shift work, and can accurately acquire work-residence information for both ordinary users and users who do not work a seven-day work cycle or an eight-hour workday, thereby effectively improving the accuracy and universality of user work-residence information analysis.
[0060] In one embodiment, step S1 includes:
[0061] The system acquires user zipper entry and exit data from multiple base stations, and discretizes the zipper entry and exit data after data cleaning according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station; wherein, the data cleaning process includes removing short-term zipper data with user dwell time less than a preset time threshold.
[0062] It should be noted that, in order to prevent interference from other daily user behaviors during subsequent spectrum analysis of user behavior, short-term chain data with user dwell time less than a preset time threshold (e.g., 2 hours) are first removed. For example, if the time difference between a user's entry and exit from a certain base station is less than two hours, the user's behavior at that base station is likely not going to work or resting at home, but rather a daily activity such as shopping at a supermarket or going to the gym. By cleaning this type of short-term chain data, the accuracy of subsequent analysis of user work-residence behavior can be further improved, and the computational efficiency of the analysis process can be increased.
[0063] In one embodiment, step S6 includes:
[0064] The candidate base stations are combined in pairs to obtain multiple candidate base station combinations, and it is determined whether each candidate base station combination meets the preset work-residence characteristic conditions.
[0065] If the ingress / egress cycle error of two candidate base stations in the candidate base station combination is less than the preset error threshold, and the building label type of at least one of the two candidate base stations is residential, then the candidate base station combination is determined to meet the work-residence characteristic conditions.
[0066] Select the target base station combination that meets the work-residence characteristics from all candidate base station combinations;
[0067] The user's work and residence information is obtained based on the target base station combination.
[0068] In this embodiment, when determining whether each candidate base station combination meets the preset work-residence characteristic conditions, it can first be determined whether the candidate base station combination has a residential building label (which can be one base station or two base stations). This is because only when the combination has a base station with a residential building label can it be said that the base station combination has the user's work-residence characteristics. In addition, since the user's workplace may also be in a place with a residential building label, it is possible that both base stations in the combination have residential building labels. Then, it is determined whether the entry and exit cycle error of the two base stations in this base station combination is less than a preset error threshold. It can be understood that the entry and exit frequency of a user at their workplace is generally not too different from the entry and exit frequency of their residence. Correspondingly, the error of the entry and exit cycle of the user at these two base stations will not be too large (the entry and exit cycle and the entry and exit frequency are reciprocals of each other). For example, if a user's work frequency is six or five cycles per week, and the user's entry and exit frequency at their residence is seven cycles, then the entry and exit cycles of the base stations corresponding to the user in these two places will not be too different. If the entry and exit cycle error of a certain base station combination is too large, for example, if a user enters and exits at one base station seven times a week and at another base station three times a week, then the candidate base station combination formed by these two base stations obviously does not conform to the normal user work-residence behavior characteristics, and such combinations will be screened out.
[0069] Finally, one or more target base station combinations that meet the work-residence characteristic conditions are obtained, and then the user's work-residence information is obtained based on these target base station combinations. When multiple target base station combinations are obtained, the corresponding work-residence information results can be output in order of priority. For example, the combination with the smaller input / output cycle error between two base stations can be sorted first.
[0070] The work-residence information acquisition method provided in this application, by filtering candidate base station combinations based on entry / exit cycle error and building tag attributes, can eliminate candidate base station combinations that do not conform to the actual work-residence characteristics of users, thereby further improving the accuracy of user work-residence information analysis.
[0071] In one embodiment, obtaining the user's work-residence information based on the target base station combination includes:
[0072] The base station with the larger ingress / egress period in the target base station combination is identified as the user's work base station, and the other base station in the target base station combination is identified as the user's residential base station;
[0073] The user's work-residence information is obtained based on the target base station combination; wherein, the work-residence information includes one or more of the following: workplace geographic information, residence geographic information, workplace entry and exit cycle information, and residence entry and exit cycle information.
[0074] It is understandable that, considering that users typically return to their residences daily but do not usually go to work every day (users generally have weekends or monthly days off), the frequency of a user's entry and exit from their residences is inevitably higher than their frequency of entry and exit from their workplaces. Consequently, the user's entry and exit cycle at the workplace will be relatively longer. Therefore, in this embodiment, after obtaining the target base station combination, the base station with the larger entry and exit cycle in the base station combination is identified as the user's workplace base station, and the other base station is identified as the user's residential base station. After determining the user's workplace-residence base station combination, the user's work-residence information can be obtained based on the corresponding geographical information, attribute information, and user entry and exit time information of the base stations. This information may include one or more of the following: workplace geographical information, residential geographical information, workplace entry and exit cycle information, and residential entry and exit cycle information.
[0075] The work-residence information acquisition method provided in this application divides the base stations corresponding to the user's workplace and residence according to the actual application scenario, so that the final analysis of the user's work-residence information can better reflect the user's real situation, thereby greatly improving the accuracy and universality of work-residence information analysis.
[0076] In one embodiment, after sorting all base stations in ascending order of their ingress and egress periods and selecting several candidate base stations with high rankings, and before combining the candidate base stations in pairs to obtain multiple candidate base station combinations, the method further includes:
[0077] Based on the location information of the candidate base stations, corresponding building labels are matched from a preset vector map, and the building labels are marked to correspond with the candidate base stations.
[0078] It should be noted that, for building tags of base stations, the base station information carrying building tag information can be obtained when acquiring user signaling data, but this will occupy unnecessary computing and storage space. Therefore, in this embodiment of the application, after selecting candidate base stations, the corresponding building tags are matched from the preset vector map according to the location information of each candidate base station to tag each candidate base station, thereby effectively reducing the computing and storage load of the system.
[0079] Based on the above solution, and to facilitate a better understanding of the work-residence information acquisition method provided in this application's embodiments, the following detailed explanation is provided:
[0080] It should be noted that the method for obtaining work and residence information provided in this application can take into account users who do not work within a seven-day work cycle, as well as users who do not work an eight-hour workday, and has general applicability to users with any work system.
[0081] This application embodiment uses Fourier transform to perform frequency domain spectrum analysis on user entry and exit behavior at base stations, thereby obtaining the user's work-residence information. Fourier transform avoids the time domain analysis relied upon by traditional methods, thus covering work-residence analysis for users with non-weekend work schedules and night shifts. It effectively solves the problems of inaccuracy and omissions in user analysis caused by traditional methods relying on manually defined empirical thresholds for time.
[0082] This application primarily targets user groups whose workplaces are fixed and whose residences have distinct characteristics (such as residential areas or dormitory buildings) for work-residence information analysis. Please refer to [link to relevant documentation]. Figure 2 Specifically, it includes the following steps:
[0083] 1. Discretization coding:
[0084] Since user behavior is time-series and has a continuous time spectrum, its time spectrum must first be encoded to facilitate spectral analysis. Here, we use bipolar non-return-to-zero (NRZ) coding. NRZ coding refers to coding that does not return to zero at the end of a symbol period. The code occupies the entire symbol width and is a commonly used digital baseband transmission coding method, characterized by its simplicity and robustness. Because this method does not involve signal transmission and has no requirements for signal reception synchronization, bipolar NRZ coding is used here.
[0085] To prevent interference from other daily user behaviors during subsequent spectrum analysis, short-duration zipper data with a user dwell time of less than 2 hours is first removed. Then, the user's long-duration base station zipper data for the current month is divided by base station and digitally encoded accordingly. Specifically, entering a base station is marked as "1", and leaving a base station is marked as "-1", thus obtaining the time-series discrete signal of the user's entry and exit behavior at each base station. Its expression is:
[0086]
[0087] Among them, t in t represents the time when a user enters base station S. out This represents the time the user leaves base station S. It's worth noting that, to reduce the number of subsequent sampling points and improve computational efficiency, the user's entry and exit times are rounded down to the nearest hour. A timing diagram of their entry and exit behavior is shown below. Figure 3 As shown.
[0088] 2. Discrete summation:
[0089] By discretely accumulating the user-base station entry / exit behavior time-series discrete signals obtained in the previous step in the time domain, we can obtain the user's dwell time status time-series sampling signal (dwell time series) under each base station. Its expression is as follows:
[0090]
[0091] Where n∈[0,24) and n∈N, N is the set of natural numbers, Δt=1h represents the discrete-time sampling interval, t s This indicates the time the user spends at the S base station.
[0092] A schematic diagram of the user dwell time sampling signal is shown below. Figure 4 As shown.
[0093] 3. Fourier Transform
[0094] The Discrete Fourier Transform (DFT) is a commonly used analytical method in signal processing. The following formula is used to perform a DFT on the user-resident state time-series sampled signal obtained in the previous step:
[0095]
[0096] Among them, f s (nΔt) is a continuous time-domain signal f s(t) A discrete periodic sequence (i.e., the dwell time sequence mentioned above) is sampled at equal intervals in the time domain, with a sampling period of t = T / N, where T is the period of the continuous signal and N is the number of sampling points. Here, the sampling period is taken as 1 hour and the number of sampling points is taken as 24. After DFT transformation, the spectral characteristics of the discrete periodic sequence can be obtained, such as... Figure 5 As shown.
[0097] By performing a Fourier transform on the time-series sampled signal of the user's dwell time, the user's temporal behavior at the base station can be mapped onto the frequency spectrum. The spectral function is a function that intuitively reflects the frequency domain characteristics of a time-domain function; it can analyze different frequency components, which are manifested in different peaks of the amplitude spectrum. The frequency corresponding to the peak with the largest amplitude within the periodic spectrum is the user's entry / exit frequency at that base station, and its reciprocal is the user's entry / exit period at that base station.
[0098] 4. Analyze the work-residence cycle:
[0099] The user entry and exit cycles at base stations obtained from the previous spectrum analysis are summarized to obtain a user-base station entry and exit cycle table. Then, all base stations are sorted according to their behavior cycles, and the top 10 base stations with the highest frequency, i.e., the shortest cycle, are selected (the specific number can be set according to requirements).
[0100] Then, based on the geographical locations of these 10 base stations and their correspondence with the actual vector map, the buildings where these 10 base stations are located are found and labeled.
[0101] Then, find two base stations among these base stations with a cycle error of no more than 1 day, and determine whether either of these base stations has a building label belonging to the "residential area" category. If so, then this pair of buildings are the user's "workplace" and "residence" respectively, and the cycle with the smaller frequency of entry and exit between the two is the user's work cycle.
[0102] Furthermore, it should be noted that the Discrete Fourier Transform (DFT) in this embodiment can be accelerated using the Fast Fourier Transform (FFT). The Fast Fourier Transform (FFT) can significantly improve the computation speed of spectral analysis by utilizing the repetitive and periodic nature of the DFT calculation process. For a discrete signal of length N, one DFT requires calculating N... 2 This requires N multiplications and N(N-1) additions, while a single FFT only requires... Multiplication and Addition. For example, when analyzing a user's signaling data for a complete month, with N = 30 * 24 sampling points, using FFT can greatly improve efficiency.
[0103] Compared with the prior art, the embodiments of this application have the following beneficial effects:
[0104] The work-residence information acquisition method provided in this application can consider users who work outside the seven-day work cycle, as well as those working in places with complex personnel mobility. It can adapt to users who work at any time, is not dependent on the definition of time periods, and has general applicability to workers in a wide range of workplaces with all work cycle systems.
[0105] The work-residence information acquisition device provided in the embodiments of this application is described below. The work-residence information acquisition device described below can be referred to in correspondence with the work-residence information acquisition method described above.
[0106] Please see Figure 6 This application provides a work-residence information acquisition device, comprising:
[0107] Data encoding module 1 is used to acquire the user's zipper entry and exit data at multiple base stations and discretize and encode it according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station.
[0108] The sequence acquisition module 2 is used to perform discrete accumulation and filling on each of the input and output time-series discrete signals in the time domain according to the user's dwell time at each base station, so as to obtain the dwell time sequence corresponding to each base station.
[0109] The frequency acquisition module 3 is used to perform Fourier transform processing on each of the dwell time series to obtain the spectrum corresponding to each dwell time series;
[0110] The period determination module 4 is used to determine the user's entry and exit period at the corresponding base station based on the amplitude peak value in each spectrum.
[0111] Candidate base station selection module 5 is used to sort all base stations in ascending order of entry and exit cycles and select several candidate base stations with higher rankings.
[0112] The work-residence information acquisition module 6 is used to combine the candidate base stations in pairs to obtain multiple candidate base station combinations, and based on the entry and exit cycle error of each candidate base station combination and the building tags of each candidate base station, to select target base station combinations that meet the work-residence characteristic conditions, and to obtain the user's work-residence information based on the target base station combinations.
[0113] In one embodiment, the data encoding module 1 is specifically used for:
[0114] The system acquires user zipper entry and exit data from multiple base stations, and discretizes the zipper entry and exit data after data cleaning according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station; wherein, the data cleaning process includes removing short-term zipper data with user dwell time less than a preset time threshold.
[0115] In one embodiment, the work-residence information acquisition module 6 is specifically used for:
[0116] The candidate base stations are combined in pairs to obtain multiple candidate base station combinations, and it is determined whether each candidate base station combination meets the preset work-residence characteristic conditions.
[0117] If the ingress / egress cycle error of two candidate base stations in the candidate base station combination is less than the preset error threshold, and the building label type of at least one of the two candidate base stations is residential, then the candidate base station combination is determined to meet the work-residence characteristic conditions.
[0118] Select the target base station combination that meets the work-residence characteristics from all candidate base station combinations;
[0119] The user's work and residence information is obtained based on the target base station combination.
[0120] In one embodiment, obtaining the user's work-residence information based on the target base station combination includes:
[0121] The base station with the larger ingress / egress period in the target base station combination is identified as the user's work base station, and the other base station in the target base station combination is identified as the user's residential base station;
[0122] The user's work-residence information is obtained based on the target base station combination; wherein, the work-residence information includes one or more of the following: workplace geographic information, residence geographic information, workplace entry and exit cycle information, and residence entry and exit cycle information.
[0123] In one embodiment, a building labeling module is also included, for:
[0124] Based on the location information of the candidate base stations, corresponding building labels are matched from a preset vector map, and the building labels are marked to correspond with the candidate base stations.
[0125] In one embodiment, the discretization encoding is an encoding method using bipolar non-return-to-zero codes.
[0126] In one embodiment, the Fourier transform processing is performed using the Fast Fourier Transform (FFT) calculation method.
[0127] It is understood that the above-described device embodiments correspond to the method embodiments of this application. The work-residence information acquisition device provided in this application can implement the work-residence information acquisition method provided in any one of the method embodiments of this application.
[0128] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 can call a computer program in the memory 730 to execute the steps of the job information acquisition method, such as including:
[0129] S1. Acquire user zipper entry and exit data at multiple base stations and discretize and encode the data according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station.
[0130] S2. Based on the user's dwell time at each base station, each of the aforementioned discrete entry and exit time-series signals is discretely accumulated and filled in the time domain to obtain the dwell time sequence corresponding to each base station.
[0131] S3. Perform Fourier transform processing on each of the dwell time series to obtain the spectrum corresponding to each dwell time series;
[0132] S4. Determine the user's entry and exit cycle at the corresponding base station based on the amplitude peak value in each of the spectrums.
[0133] S5. Sort all base stations in ascending order of entry and exit cycles, and select several candidate base stations with the highest order.
[0134] S6. The candidate base stations are combined in pairs to obtain multiple candidate base station combinations. Based on the entry and exit cycle error of each candidate base station combination and the building labels of each candidate base station, target base station combinations that meet the work-residence characteristic conditions are selected. The user's work-residence information is obtained based on the target base station combinations.
[0135] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0136] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the job information acquisition method provided in the above embodiments, such as:
[0137] S1. Acquire user zipper entry and exit data at multiple base stations and discretize and encode the data according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station.
[0138] S2. Based on the user's dwell time at each base station, each of the aforementioned discrete entry and exit time-series signals is discretely accumulated and filled in the time domain to obtain the dwell time sequence corresponding to each base station.
[0139] S3. Perform Fourier transform processing on each of the dwell time series to obtain the spectrum corresponding to each dwell time series;
[0140] S4. Determine the user's entry and exit cycle at the corresponding base station based on the amplitude peak value in each of the spectrums.
[0141] S5. Sort all base stations in ascending order of entry and exit cycles, and select several candidate base stations with the highest order.
[0142] S6. The candidate base stations are combined in pairs to obtain multiple candidate base station combinations. Based on the entry and exit cycle error of each candidate base station combination and the building labels of each candidate base station, target base station combinations that meet the work-residence characteristic conditions are selected. The user's work-residence information is obtained based on the target base station combinations.
[0143] On the other hand, embodiments of this application also provide a processor-readable storage medium storing a computer program for causing a processor to perform the steps of the methods provided in the above embodiments, such as including:
[0144] S1. Acquire user zipper entry and exit data at multiple base stations and discretize and encode the data according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station.
[0145] S2. Based on the user's dwell time at each base station, each of the aforementioned discrete entry and exit time-series signals is discretely accumulated and filled in the time domain to obtain the dwell time sequence corresponding to each base station.
[0146] S3. Perform Fourier transform processing on each of the dwell time series to obtain the spectrum corresponding to each dwell time series;
[0147] S4. Determine the user's entry and exit cycle at the corresponding base station based on the amplitude peak value in each of the spectrums.
[0148] S5. Sort all base stations in ascending order of entry and exit cycles, and select several candidate base stations with the highest order.
[0149] S6. The candidate base stations are combined in pairs to obtain multiple candidate base station combinations. Based on the entry and exit cycle error of each candidate base station combination and the building labels of each candidate base station, target base station combinations that meet the work-residence characteristic conditions are selected. The user's work-residence information is obtained based on the target base station combinations.
[0150] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).
[0151] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0152] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A method for obtaining work-residence information, characterized in that, include: The system acquires user data for entering and exiting multiple base stations and discretizes and encodes it according to the user's entry and exit behavior to obtain the discrete entry and exit timing signal corresponding to each base station. Based on the user's dwell time at each base station, each of the aforementioned discrete input / output timing signals is discretely accumulated and filled in the time domain to obtain the dwell time sequence corresponding to each base station. Perform Fourier transform on each of the aforementioned residence time series to obtain the spectrum corresponding to each residence time series; The user's entry and exit cycle at the corresponding base station is determined based on the amplitude peak value in each of the aforementioned spectra; All base stations are sorted in ascending order of their entry and exit cycles, and several candidate base stations with the highest entry and exit cycles are selected. The candidate base stations are combined in pairs to obtain multiple candidate base station combinations. Based on the ingress and egress period error of each candidate base station combination and the building labels of each candidate base station, target base station combinations that meet the work-residence characteristic conditions are selected. The user's work-residence information is obtained based on the target base station combinations.
2. The method for obtaining work-residence information according to claim 1, characterized in that, The process of acquiring user entry and exit data at multiple base stations and discretizing and encoding it according to the user's entry and exit behavior to obtain the entry and exit time-series discrete signal corresponding to each base station includes: The system acquires user zipper entry and exit data from multiple base stations, and discretizes the zipper entry and exit data after data cleaning according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station; wherein, the data cleaning process includes removing short-term zipper data with user dwell time less than a preset time threshold.
3. The method for obtaining work-residence information according to claim 1, characterized in that, The candidate base stations are combined in pairs to obtain multiple candidate base station combinations. Based on the ingress / egress cycle error of each candidate base station combination and the building tags of each candidate base station, target base station combinations that meet the work-residence characteristic conditions are selected. Based on the target base station combinations, the user's work-residence information is obtained, including: The candidate base stations are combined in pairs to obtain multiple candidate base station combinations, and it is determined whether each candidate base station combination meets the preset work-residence characteristic conditions. If the ingress / egress cycle error of two candidate base stations in the candidate base station combination is less than the preset error threshold, and the building label type of at least one of the two candidate base stations is residential, then the candidate base station combination is determined to meet the work-residence characteristic conditions. Select the target base station combination that meets the work-residence characteristics from all candidate base station combinations; The user's work and residence information is obtained based on the target base station combination.
4. The method for obtaining work-residence information according to claim 1, characterized in that, The process of obtaining the user's work-residence information based on the target base station combination includes: The base station with the larger ingress / egress period in the target base station combination is identified as the user's work base station, and the other base station in the target base station combination is identified as the user's residential base station; The user's work-residence information is obtained based on the target base station combination; wherein, the work-residence information includes one or more of the following: workplace geographic information, residence geographic information, workplace entry and exit cycle information, and residence entry and exit cycle information.
5. The method for obtaining work-residence information according to claim 1, characterized in that, After sorting all base stations in ascending order of their ingress and egress cycles and selecting several candidate base stations with high rankings, and before combining these candidate base stations in pairs to obtain multiple candidate base station combinations, the process further includes: Based on the location information of the candidate base stations, corresponding building labels are matched from a preset vector map, and the building labels are marked to correspond with the candidate base stations.
6. The method for obtaining work-residence information according to claim 1, characterized in that, The discretization encoding adopts a bipolar non-return-to-zero code encoding method.
7. The method for obtaining work-residence information according to claim 1, characterized in that, The Fourier transform processing is performed using the Fast Fourier Transform (FFT) calculation method.
8. A work-residence information acquisition device, characterized in that, include: The data encoding module is used to acquire the user's zipper entry and exit data at multiple base stations and discretize and encode it according to the user's entry and exit behavior to obtain the entry and exit time sequence discrete signal corresponding to each base station. The sequence acquisition module is used to perform discrete accumulation and filling on each of the input and output time-series discrete signals in the time domain according to the user's dwell time at each base station, so as to obtain the dwell time sequence corresponding to each base station. The frequency acquisition module is used to perform Fourier transform processing on each of the dwell time series to obtain the spectrum corresponding to each dwell time series; The period determination module is used to determine the user's entry and exit period at the corresponding base station based on the amplitude peak value in each of the spectrums. The candidate base station selection module is used to sort all base stations in ascending order of their ingress and egress cycles and select several candidate base stations that rank higher. The work-residence information acquisition module is used to combine the candidate base stations in pairs to obtain multiple candidate base station combinations. Based on the entry and exit cycle error of each candidate base station combination and the building tags of each candidate base station, the module selects target base station combinations that meet the work-residence characteristic conditions and obtains the user's work-residence information based on the target base station combinations.
9. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the job and residence information acquisition method according to any one of claims 1 to 7.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the job and residence information acquisition method according to any one of claims 1 to 7.